Sandeep Menon

+1 I am facing same issue while running this on cloud servers.

> Thanks @CCInc! We may actually define a similar `convert_sync_batchnorm` function in TorchSparse to convert `BatchNorm` into its synchronized version for both normal and sparse tensors. I would love to...

I am having some trouble with the installation after my Ubuntu 22.04 update. Getting an error that the compiler version is mismatching. explained in this issue #189 Still trying to...

That's great! Thank you @moritzgloeckl I'll start building my automated pipelines with this.

How did you import `auto_fp16` in the latest mmcv?

@xinshuoweng Eagerly waiting for the code.

@mattgiamou Thank you so much for the insights. No inconvenience at all. Will be on the lookout for the python functionality. You mentioned the matlab code does not make this...

Thank you @mattgiamou

@mattgiamou Reopening the issue for additional clarification. I used SLAM to get the trajectory of two rigidly connected monocular cameras. They are temporally calibrated. In such scenario the scale of...

Thank @mattgiamou you for explaining the scale drift issue. Is there something that can be done in the data collection to avoid this issue? > Actually, my point about constant...